PubMed
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| S2_API_KEY | No | Semantic Scholar API key. Relaxes rate limits for Semantic Scholar requests. | |
| NCBI_API_KEY | No | NCBI API key. Raises NCBI rate limits from 3 to 10 requests per second. | |
| EUROPEPMC_EMAIL | No | Email identifier for the Europe PMC polite pool. | |
| UNPAYWALL_EMAIL | No | Email address used to enable the Unpaywall fallback in pubmed_fetch_fulltext. Any valid email works. | |
| DRUGBANK_API_KEY | No | DrugBank API key required to enable the drugbank_search tool. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pubmed_searchC | Search PubMed for biomedical articles. |
| pubmed_fetchA | Fetch detailed article metadata by PubMed IDs. |
| pubmed_summaryA | Get concise summaries of articles — faster than pubmed_fetch. Up to 50 PMIDs per request. |
| pubmed_find_relatedC | Find articles related to a source PubMed article. |
| pubmed_citation_searchB | Resolve partial citation to PMID using NCBI's citation matcher. At least one field required. More fields = better match. |
| pubmed_europepmc_searchA | Search Europe PMC — broader than PubMed: includes preprints, patents, Agricola. |
| pubmed_spell_checkA | Spell-check a biomedical query using NCBI's ESpell service. Useful for query refinement before searching. |
| pubmed_lookup_meshB | Search and explore MeSH (Medical Subject Headings) vocabulary. |
| pubmed_convert_idsA | Convert between DOI, PMID, and PMCID. Only resolves articles indexed in PubMed Central. |
| pubmed_fetch_fulltextB | Fetch full-text articles via PMC → Europe PMC → Unpaywall chain. |
| pubmed_format_citationsC | Generate formatted citations for articles. |
| pubmed_clinical_trialsC | Search ClinicalTrials.gov for clinical studies. |
| pubmed_semantic_scholarA | Search or analyze papers via Semantic Scholar API (citations, influence, references). Use search_mode='search' for keyword search, or 'paper' with paper_id (DOI, PMID prefixed with 'PMID:', or Semantic Scholar ID) for deep analysis. |
| openfda_adverse_eventsB | Query FDA Adverse Event Reporting System (FAERS) for drug side effects. |
| openfda_drug_labelC | Get FDA drug label information: indications, warnings, dosage, mechanism. |
| openfda_drug_enforcementC | Query FDA enforcement reports (recalls, warnings, market withdrawals). |
| drugbank_searchB | Search DrugBank for drug information: targets, enzymes, interactions. Requires DRUGBANK_API_KEY env var (free key at https://go.drugbank.com). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Each tool targets a distinct source, action, or resource: search vs. summary vs. fetch vs. full-text vs. citation matching vs. ID conversion, with separate tools for Europe PMC, ClinicalTrials.gov, Semantic Scholar, FDA, and DrugBank. Overlaps are minimal and well-clarified by descriptions.
All names use snake_case with a source prefix (pubmed_, openfda_, drugbank_), which is predictable. However, the pubmed_ group mostly follows verb_noun while openfda_ tools use noun phrases, a minor deviation.
17 tools is slightly above the ideal 3–15 range but reasonable for a broad biomedical literature and drug information server spanning multiple APIs and workflows. Each tool appears to earn its place.
The surface covers the full literature research lifecycle: query refinement, search across multiple databases, summaries, metadata, full text, citation resolution, ID conversion, formatting, related articles, MeSH lookup, clinical trials, and drug safety/label data. No obvious gaps for the stated domain.